© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 212
    Prev
    Next
    INDEX
    Explanations

    mentions of government departments, specifically the Interior Department

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Interior" related to government or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chers
    -0.79
    fleet
    -0.76
    fortune
    -0.73
    owder
    -0.73
    colo
    -0.72
    onsense
    -0.71
    urai
    -0.70
    etimes
    -0.69
    ieving
    -0.69
    bring
    -0.69
    POSITIVE LOGITS
     Interior
    0.98
     ministry
    0.95
     Ministry
    0.88
     Institution
    0.83
     Affairs
    0.76
     minister
    0.75
     Department
    0.72
     Secretary
    0.72
     Defense
    0.71
     Passage
    0.71
    Activations Density 0.008%

    No Known Activations